Instantiate a PreTrainedBertModel from a pre-trained model file. Download and cache the pre-trained model file if needed.

Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results

Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results

Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results

Initialize the weights.

:param path: path to merge_table

r"""Loads the optimizer state. Arguments: state_dict (dict): optimizer state. Should be an object returned fr

:param path: path to merge_table with subword-nmt format

Context manager which seeds the NumPy PRNG with the specified seed and restores the state afterward

Extract a de-duped collection (set) of text from a file. Expected file format is one item per line.

Args: input_dict (dict): all the values will be reduced average (bool): whether to do average or sum Reduce the values in the

Re-start from checkpoint

Wrapper function for s3 requests in order to create more helpful error messages.